© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91161
    Prev
    Next
    INDEX
    Explanations

    United Nations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UN
    -0.63
    car
    -0.61
    WEBPACK
    -0.50
    })));
    -0.49
    يميديا
    -0.47
     lavage
    -0.47
    ContentAsync
    -0.47
    haya
    -0.46
    WindowConstants
    -0.46
     GenerationType
    -0.45
    POSITIVE LOGITS
    TagMode
    0.71
    adaptiveStyles
    0.67
     समीक्षक
    0.67
     MaterialApp
    0.59
    MigrationBuilder
    0.57
    Sì
    0.56
    +#+
    0.56
    PerformLayout
    0.56
     specification
    0.54
     وتسجيلات
    0.54
    Activations Density 0.416%

    No Known Activations